CN109522483A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN109522483A CN109522483A CN201811352882.2A CN201811352882A CN109522483A CN 109522483 A CN109522483 A CN 109522483A CN 201811352882 A CN201811352882 A CN 201811352882A CN 109522483 A CN109522483 A CN 109522483A
- Authority
- CN
- China
- Prior art keywords
- information
- recommendation information
- feature vector
- recommendation
- eigenvector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for pushed information.One specific embodiment of this method includes: the attribute information for obtaining target user；First eigenvector is generated according to the attribute information of target user；Obtain the recommendation information of target object；Second feature vector is generated according to recommendation information；Based on first eigenvector, second feature vector and prediction model trained in advance, target user is generated to the response intention of recommendation information；Target users did respond recommendation information is indicated in response to the response intention that prediction model generates, and pushes recommendation information to the terminal of target user.This embodiment offers the mechanism that a kind of attribute information based on user and recommendation information carry out information push, improve information pushing efficiency.
Description
Technical field
The invention relates to field of computer technology, the more particularly, to method and apparatus of pushed information.
Background technique
Information push is also known as " Web broadcast " by certain technical standard or agreement, on the internet by pushing away
The information of user's needs is sent to reduce a technology of information overload.Information advancing technique by active push information to user,
User can be reduced the time spent in searching on network.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for pushed information.
In a first aspect, some embodiments of the present application provide a kind of method for pushed information, this method comprises: obtaining
Take the attribute information of target user；First eigenvector is generated according to the attribute information of target user；Obtain pushing away for target object
Recommend information；Second feature vector is generated according to recommendation information；Based on first eigenvector, second feature vector and training in advance
Prediction model, generate target user to the response intention of recommendation information；The response intention instruction generated in response to prediction model
Target users did respond recommendation information pushes recommendation information to the terminal of target user.
In some embodiments, method further include: obtain the attribute information of target object；Believed according to the attribute of target object
Breath generates third feature vector；It is raw and based on first eigenvector, second feature vector and prediction model trained in advance
At target user to the response intention of recommendation information, comprising: by first eigenvector, second feature vector sum third feature vector
It is input to prediction model trained in advance, generates target user to the response intention of recommendation information.
In some embodiments, recommendation information is generated via following steps: selection is preset for target object
Recommendation information set of segments in recommendation information segment be combined, obtain the set of recommendation information fragment combination；For collection
Recommendation information fragment combination in conjunction: the feature vector of the recommendation information fragment combination is generated；By the recommendation information fragment combination
Feature vector, first eigenvector and second feature vector be input in advance trained Rating Model, generate the recommendation
Cease the score of fragment combination；Recommendation information is generated according to the recommendation information fragment combination that set mid-score meets preset condition.
In some embodiments, recommendation is generated according to the recommendation information fragment combination that set mid-score meets preset condition
Breath, comprising: obtain the acquisition modes information of pre-set target object；Merge the recommendation that set mid-score meets preset condition
Information segment combination and acquisition modes information, obtain recommendation information.
In some embodiments, according to recommendation information generate second feature vector, comprising: obtain recommendation information include with
At least one of in lower item of information: keyword, scene information and functional information；According to acquired item of information second feature to
Amount.
Second aspect, some embodiments of the present application provide a kind of device for pushed information, which includes:
One acquiring unit is configured to obtain the attribute information of target user；First generation unit, is configured to according to target user's
Attribute information generates first eigenvector；Second acquisition unit is configured to obtain the recommendation information of target object；Second generates
Unit is configured to generate second feature vector according to recommendation information；Third generation unit, be configured to based on fisrt feature to
Amount, second feature vector and prediction model trained in advance generate target user to the response intention of recommendation information；Push is single
Member is configured in response to the response intention instruction target users did respond recommendation information of prediction model generation, to target user's
Terminal pushes recommendation information.
In some embodiments, device further include: third acquiring unit is configured to obtain the attribute letter of target object
Breath；4th generation unit is configured to generate third feature vector according to the attribute information of target object；And third generates list
Member is further configured to: first eigenvector, second feature vector sum third feature vector are input to the pre- of training in advance
Model is surveyed, generates target user to the response intention of recommendation information.
In some embodiments, device further includes recommendation information generation unit, and recommendation information generation unit includes: a group zygote
Unit is configured to select to carry out group for the recommendation information segment in the pre-set recommendation information set of segments of target object
It closes, obtains the set of recommendation information fragment combination；First generates subelement, is configured to for the recommendation information segment in set
Combination: the feature vector of the recommendation information fragment combination is generated；By the feature vector of the recommendation information fragment combination, fisrt feature
Vector and second feature vector are input to Rating Model trained in advance, generate the score of the recommendation information fragment combination；The
Two generate subelement, and the recommendation information fragment combination for being configured to meet according to set mid-score preset condition generates recommendation
Breath.
In some embodiments, recommendation information generates subelement, is further configured to: first obtains subelement, is matched
It is set to the acquisition modes information for obtaining pre-set target object；Merge subelement, is configured to merge set mid-score symbol
The recommendation information fragment combination and acquisition modes information for closing preset condition, obtain recommendation information.
In some embodiments, the second generation unit, comprising: second obtains subelement, is configured to obtain recommendation information
At least one of in the following item of information for including: keyword, scene information and functional information；Third generates subelement, according to institute
The item of information of acquisition generates second feature vector.
The third aspect, some embodiments of the present application provide a kind of equipment, comprising: one or more processors；Storage
Device is stored thereon with one or more programs, when said one or multiple programs are executed by said one or multiple processors,
So that said one or multiple processors realize such as the above-mentioned method of first aspect.
Fourth aspect, some embodiments of the present application provide a kind of computer-readable medium, are stored thereon with computer
Program realizes such as first aspect above-mentioned method when the program is executed by processor.
Method and apparatus provided by the embodiments of the present application for pushed information, the attribute by obtaining target user are believed
Breath；First eigenvector is generated according to the attribute information of target user；Obtain the recommendation information of target object；According to recommendation information
Generate second feature vector；Based on first eigenvector, second feature vector and prediction model trained in advance, target is generated
Response intention of the user to recommendation information；Target users did respond recommendation is indicated in response to the response intention that prediction model generates
Breath pushes recommendation information to the terminal of target user, provides a kind of attribute information based on user and recommendation information carries out
The mechanism of information push, improves information pushing efficiency.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that some of the application can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the application；
Fig. 3 is a schematic diagram according to the application scenarios of the method for pushed information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for pushed information of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for pushed information of the application；
Fig. 6 is adapted for showing for the structure of the computer system of the server or terminal of realizing some embodiments of the present application
It is intended to.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for pushed information of the application or the implementation of the device for pushed information
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..It can be equipped on terminal device 101,102,103 at various client applications, such as social category application, image
Manage class application, e-commerce application, searching class application etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be the various electronic equipments with display screen, including but not limited to smart phone, tablet computer, on knee portable
Computer and desktop computer etc..When terminal device 101,102,103 is software, above-mentioned cited electricity may be mounted at
In sub- equipment.Multiple softwares or software module may be implemented into (such as providing Image Acquisition service or In vivo detection in it
Service), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as to installing on terminal device 101,102,103
Using the background server that offer is supported, or provide the server of Information Push Service, the available target user of server 105
Attribute information；First eigenvector is generated according to the attribute information of target user；Obtain the recommendation information of target object；According to
Recommendation information generates second feature vector；Based on first eigenvector, second feature vector and prediction model trained in advance,
Target user is generated to the response intention of recommendation information；Target users did respond is indicated in response to the response intention that prediction model generates
Recommendation information pushes recommendation information to the terminal device 101,102,103 of target user.
It should be noted that the method provided by the embodiment of the present application for pushed information can be held by server 105
Row, can also be executed, correspondingly, the device for pushed information can be set in server by terminal device 101,102,103
In 105, also it can be set in terminal device 101,102,103.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software also may be implemented into
Module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the process of one embodiment of the method for pushed information according to the application is shown
200.This is used for the method for pushed information, comprising the following steps:
Step 201, the attribute information of target user is obtained.
It in the present embodiment, can for the method executing subject of pushed information (such as server shown in FIG. 1 or terminal)
To obtain the attribute information of target user first.Target user can be any user to its pushed information.Target user
Attribute information can from user draw a portrait extract, attribute information may include build-in attribute and dynamic attribute.Build-in attribute can be with
Including gender, age, occupation, educational background, marital status, level of education etc., dynamic attribute may include personal interest, geography
Position etc..User's portrait can be obtained by the historical record of the used application of user or website, for example, mentioning when user's registration
The registration information of friendship, the content of pages that user often accesses, user search for the keyword used.
Step 202, first eigenvector is generated according to the attribute information of target user.
In the present embodiment, above-mentioned executing subject can be raw according to the attribute information of the target user obtained in step 201
At first eigenvector.The vector that the entry of multiple attribute informations is converted to can combine to obtain the first spy by modes such as splicings
Levy vector.It should be noted that term vector can be intended to indicate that the vector of the feature of word, term vector can be with per one-dimensional value
Represent the feature that there is certain semanteme and grammatically explain.Wherein, feature can be for the fundamental to word into
The various information of row characterization.Above-mentioned executing subject can use the term vector that various term vector generating modes generate each entry,
It is, for example, possible to use the generations of existing term vector Core Generator (such as word2vec etc.), or utilize training neural network
Mode generates.
Step 203, the recommendation information of target object is obtained.
In the present embodiment, the recommendation information of the available target object of above-mentioned executing subject.Target object, which can be, appoints
What is the need for will be to the object that it is recommended.For example, extensive stock and service.The recommendation information of target object, which can be, to be preset
, it is also possible to choose what recommendation information fragment combination obtained from pre-set recommendation information set of segments.As an example,
Target object be credit card to be recommended, recommendation information may include " it is said that everyone can have a credit card? bid to host letter
It is single, fully withdraw deposit, exempt from annual fee ".
In some optional implementations of the present embodiment, recommendation information be can be via following steps generation: selection
It is combined for the recommendation information segment in the pre-set recommendation information set of segments of target object, obtains recommendation information piece
The set of Duan Zuhe；For the recommendation information fragment combination in set: generating the feature vector of the recommendation information fragment combination；It will
Feature vector, first eigenvector and the second feature vector of the recommendation information fragment combination are input to scoring trained in advance
Model generates the score of the recommendation information fragment combination；Meet the recommendation information segment group of preset condition according to set mid-score
Symphysis is at recommendation information.Recommendation information is generated by recommendation information fragment combination, further improves the spirit of recommendation information generation
Activity.
In this implementation, Rating Model can be used for characterizing the feature vector and recommendation information fragment combination of input
The corresponding relationship of score, after the score of Rating Model output can be used for characterizing the recommendation information that user receives generation, response
The probability of the recommendation information.Rating Model can be using the sampling feature vectors in sample set as input, will be identified
Sample of users is used as the response results of recommendation information and exports, the initial logistic regression (Logistic Regression) of training,
Random forest (random forest), iteration decision tree (gradient boosting decision tree) or supporting vector
What the models such as machine (Support Vector Machine) obtained.The recommendation that sample in sample set can be pushed based on history
Acquisition of information.Herein, by taking target object is credit card as an example, recommendation information segment may include " without changing money ", " exempt from
Expense is bid to host ", " fully withdrawing deposit " and " exempting from annual fee " etc..In addition, score, which meets preset condition, can refer to that score is more than preset threshold
Or score is most high.
In some optional implementations of the present embodiment, the recommendation information piece of preset condition is met according to set mid-score
Section combination producing recommendation information, comprising: obtain the acquisition modes information of pre-set target object；Merge set mid-score symbol
The recommendation information fragment combination and acquisition modes information for closing preset condition, obtain recommendation information.As an example, acquisition modes information
It may include: " clicking certain link can obtain ", " going to certain position that can obtain " and " dialing certain phone can obtain " etc..This
Outside, it can also include the mode for quitting the subscription of this type of information push in recommendation information, be quit the subscription of for example, replying.
Step 204, second feature vector is generated according to recommendation information.
In the present embodiment, above-mentioned executing subject can generate second feature according to the recommendation information obtained in step 203
Vector.The method that above-mentioned executing subject is referred to generate first eigenvector in step 202 uses natural language processing technique
Second feature vector is generated according to recommendation information.
In some optional implementations of the present embodiment, second feature vector is generated according to recommendation information, can also be wrapped
It includes: obtaining at least one in the following item of information that recommendation information includes: keyword, scene information and functional information；According to institute
The item of information second feature vector of acquisition.By taking target object is credit card as an example, recommendation information is " world to be enjoyed a trip to, without exchanging
Foreign currency, the overlength free of interest phase ", then keyword may include tourism, changing money and free of interest, and scene information may include National Travel Agency out
Trip, functional information may include bankcard consumption；Recommendation information be " it is said that everyone can have a credit card? it is bid to host simple, entirely
Volume is withdrawn deposit, and annual fee is exempted from ", then keyword may include fully withdrawing deposit and exempting from annual fee, scene information may include credit card withdraw deposit, function
Energy information may include enchashment.
In this implementation, information above item can be respectively converted into term vector by above-mentioned executing subject, then pass through spelling
It the combinations such as connects to combine to obtain second feature vector.Machine learning method can be used in upper item of information, passes through trained mould
Type extracts, can also be by manually marking to obtain.By the way that each item of information is respectively converted into term vector, further improve
The accuracy of the second feature vector of generation.
Step 205, based on first eigenvector, second feature vector and prediction model trained in advance, target is generated
Response intention of the user to recommendation information.
In the present embodiment, above-mentioned executing subject can based on generated in step 202 first eigenvector, step 204
The second feature vector of middle generation and prediction model trained in advance generate target user to the response intention of recommendation information.
Target user to the response intention of recommendation information may include indicate user whether can respond recommendation information prediction result and
The probability of user response recommendation information.The form of expression of user response recommendation information may include clicking in recommendation information to include
Link replys recommendation information and obtains the behavior of target object information.Above-mentioned executing subject can by first eigenvector,
Input of the feature vector that second feature vector or first eigenvector, second feature vector combine as prediction model,
It can also be by first eigenvector, second feature vector and other feature vectors or first eigenvector, second feature vector
And input of the obtained feature vector of other combination of eigenvectors as prediction model.
In the present embodiment, the prediction model is used to characterize the feature vector inputted and target user to recommendation information
The corresponding relationship of response intention.It can be using the sampling feature vectors in sample set as input, by the sample in sample set
Response intention is as output, training initial model-naive Bayesian (Naive Bayesian Model, NBM) or supporting vector
The model for classification such as machine (Support Vector Machine, SVM), obtains prediction model.Prediction model is also possible to
Technical staff based on to a large amount of feature vector and in response to intention statistics and pre-establish, be stored with feature vector and response
The mapping table of the corresponding relationship of intention；It equally can be technical staff to preset simultaneously based on the statistics to mass data
Store it is into above-mentioned electronic equipment, the one or more of feature vector is calculated, obtain for characterizing response intention
Calculated result calculation formula.
Step 206, target users did respond recommendation information is indicated in response to the response intention that prediction model generates, use to target
The terminal at family pushes recommendation information.
In the present embodiment, above-mentioned executing subject can the response of prediction model generation be anticipated in step 205 according to response
To instruction target users did respond recommendation information, recommendation information is pushed to the terminal of target user.As an example, above-mentioned executing subject
It can be pushed by the forms such as communication information of short message, the notification information of application software, social software to the terminal of target user
Recommendation information, recommendation information can be the formats such as text, voice, image.
With continued reference to the signal that Fig. 3, Fig. 3 are according to the application scenarios of the method for pushed information of the present embodiment
Figure.In the application scenarios of Fig. 3, server 301 obtains the attribute information 303 of the target user of using terminal 302, attribute first
Information 303 may include the following contents " male, 26 years old, like travelling "；It is special that first is generated according to the attribute information 303 of target user
Levy vector 304；The recommendation information 306 of target object 305 is obtained, target object 305 can be certain credit card, recommendation information
306 may include the following contents " enjoying a trip to the world, be not necessarily to changing money, overlength free of interest phase ... "；The is generated according to recommendation information 306
Two feature vectors 307；It is raw based on first eigenvector 304, second feature vector 307 and prediction model 308 trained in advance
At target user to the response intention 309 of recommendation information 306；Target is indicated in response to the response intention 309 that prediction model generates
User response recommendation information pushes recommendation information 306 to the terminal 302 of target user.
The attribute information that the method provided by the above embodiment of the application passes through acquisition target user；According to target user's
Attribute information generates first eigenvector；Obtain the recommendation information of target object；Second feature vector is generated according to recommendation information；
Based on first eigenvector, second feature vector and prediction model trained in advance, target user is generated to recommendation information
Response intention；Target users did respond recommendation information is indicated in response to the response intention that prediction model generates, to the end of target user
End push recommendation information, provides a kind of attribute information based on user and recommendation information carries out the mechanism of information push, mentions
The high ratio of user response recommendation information, that is, improve information pushing efficiency.
With further reference to Fig. 4, it illustrates the processes 400 of another embodiment of the method for pushed information.The use
In the process 400 of the method for pushed information, comprising the following steps:
Step 401, the attribute information of target user is obtained.
It in the present embodiment, can for the method executing subject of pushed information (such as server shown in FIG. 1 or terminal)
To obtain the attribute information of target user first.Step 402, first eigenvector is generated according to the attribute information of target user.
In the present embodiment, above-mentioned executing subject can be raw according to the attribute information of the target user obtained in step 401
At first eigenvector.
Step 403, the recommendation information of target object is obtained.
In the present embodiment, the recommendation information of the available target object of above-mentioned executing subject.
Step 404, second feature vector is generated according to recommendation information.
In the present embodiment, above-mentioned executing subject can generate second feature according to the recommendation information obtained in step 403
Vector.
Step 405, the attribute information of target object is obtained.
In the present embodiment, the attribute information of the available target object of above-mentioned executing subject.The attribute of target object is believed
Breath may include the appearance information of target object, functional information etc..The attribute information of target object can according to actual needs into
Row selection.By taking target object is credit card as an example, attribute information may include the benefits information of credit card.
Step 406, third feature vector is generated according to the attribute information of target object.
In the present embodiment, above-mentioned executing subject can be raw according to the attribute information of the target object obtained in step 405
At third feature vector.The method that above-mentioned executing subject is referred to generate first eigenvector in step 202 uses nature language
Say that processing technique generates third feature vector according to the attribute information of target object.It include the equity letter of credit card with attribute information
For breath, benefits information includes " order and take out, purchase by group, single highest is vertical subtract 77 yuan "；" specified deluxe hotel's buffet buys one
Give one "；" specified deluxe hotel lives 3 pair 2 ".Attribute information can be taken into: it takes out, purchase by group, red packet, the features such as hotel, and
It is indicated again with feature vector afterwards.
Step 407, first eigenvector, second feature vector sum third feature vector are input to prediction trained in advance
Model generates target user to the response intention of recommendation information.
In the present embodiment, above-mentioned executing subject can by first eigenvector, second feature vector sum third feature to
Amount is input to prediction model trained in advance, generates target user to the response intention of recommendation information.Prediction model can be used for
First eigenvector, second feature vector sum third feature vector and the target user for characterizing input anticipate to the response of recommendation information
To corresponding relationship, specifically establish mode may refer in step 205 be directed to prediction model description.
Step 408, target users did respond recommendation information is indicated in response to the response intention that prediction model generates, use to target
The terminal at family pushes recommendation information.
In the present embodiment, above-mentioned executing subject can the response of prediction model generation be anticipated in step 407 according to response
To instruction target users did respond recommendation information, recommendation information is pushed to the terminal of target user.
In the present embodiment, step 401, step 402, step 403, step 404, the operation of step 408 and step 201,
Step 202, step 203, step 204, the operation of step 206 are essentially identical, and details are not described herein.
Figure 4, it is seen that the method for pushed information compared with the corresponding embodiment of Fig. 2, in the present embodiment
Process 400 in third feature vector generated by the attribute information of target object, according to first eigenvector, second feature to
Amount and third feature vector generate target user to the response intention of recommendation information, as a result, life in the scheme of the present embodiment description
At response intention it is more acurrate, further improve information push accuracy.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for pushing letter
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 for pushed information of the present embodiment includes: that first acquisition unit 501, first is raw
At unit 502, second acquisition unit 503, the second generation unit 504, third generation unit 505 and push unit 506.Wherein,
First acquisition unit is configured to obtain the attribute information of target user；First generation unit, is configured to according to target user
Attribute information generate first eigenvector；Second acquisition unit is configured to obtain the recommendation information of target object；Second is raw
At unit, it is configured to generate second feature vector according to recommendation information；Third generation unit is configured to based on fisrt feature
Vector, second feature vector and prediction model trained in advance generate target user to the response intention of recommendation information；Push
Unit is configured in response to the response intention instruction target users did respond recommendation information of prediction model generation, to target user
Terminal push recommendation information.
In the present embodiment, for the first acquisition unit 501 of the device of pushed information 500, the first generation unit 502,
The specific processing of second acquisition unit 503, the second generation unit 504, third generation unit 505 and push unit 506 can be joined
Examine step 201, step 202, step 203, step 204, step 205 and the step 206 in Fig. 2 corresponding embodiment.
In some optional implementations of the present embodiment, device further include: third acquiring unit is configured to obtain mesh
Mark the attribute information of object；4th generation unit is configured to generate third feature vector according to the attribute information of target object；
And third generation unit, it is further configured to: first eigenvector, second feature vector sum third feature vector is inputted
To prediction model trained in advance, target user is generated to the response intention of recommendation information.
In some optional implementations of the present embodiment, device further includes recommendation information generation unit, and recommendation information is raw
Include: combination subelement at unit, is configured to select in the pre-set recommendation information set of segments of target object
Recommendation information segment is combined, and obtains the set of recommendation information fragment combination；First generates subelement, is configured to for collection
Recommendation information fragment combination in conjunction: the feature vector of the recommendation information fragment combination is generated；By the recommendation information fragment combination
Feature vector, first eigenvector and second feature vector be input in advance trained Rating Model, generate the recommendation
Cease the score of fragment combination；Second generates subelement, is configured to meet according to set mid-score the recommendation information of preset condition
Fragment combination generates recommendation information.
In some optional implementations of the present embodiment, recommendation information generates subelement, is further configured to: first
Subelement is obtained, is configured to obtain the acquisition modes information of pre-set target object；Merge subelement, is configured to close
And gather recommendation information fragment combination and acquisition modes information that mid-score meets preset condition, obtain recommendation information.
In some optional implementations of the present embodiment, the second generation unit, comprising: second obtains subelement, is matched
It is set at least one obtained in the following item of information that recommendation information includes: keyword, scene information and functional information；Third is raw
At subelement, second feature vector is generated according to acquired item of information.
The device provided by the above embodiment of the application, by the attribute information for obtaining target user；According to target user
Attribute information generate first eigenvector；Obtain the recommendation information of target object；According to recommendation information generate second feature to
Amount；Based on first eigenvector, second feature vector and prediction model trained in advance, target user is generated to recommendation information
Response intention；Target users did respond recommendation information is indicated in response to the response intention that prediction model generates, to target user's
Terminal pushes recommendation information, provides a kind of attribute information based on user and recommendation information carries out the mechanism of information push,
Improve information pushing efficiency.
Below with reference to Fig. 6, it illustrates the server for being suitable for being used to realize the embodiment of the present application or the departments of computer science of terminal
The structural schematic diagram of system 600.Server or terminal shown in Fig. 6 are only an example, should not be to the function of the embodiment of the present application
Any restrictions can be brought with use scope.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various movements appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
It can connect with lower component to I/O interface 605: the importation 606 including keyboard, mouse etc.；Including all
The output par, c 607 of such as cathode-ray tube (CRT), liquid crystal display (LCD) and loudspeaker etc.；Storage including hard disk etc.
Part 608；And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 passes through
Communication process is executed by the network of such as internet.Driver 610 is also connected to I/O interface 605 as needed.Detachable media
611, such as disk, CD, magneto-optic disk, semiconductor memory etc., are mounted on as needed on driver 610, in order to from
The computer program read thereon is mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer-readable medium either the two any combination.Computer-readable medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example of machine readable medium can include but is not limited to: electrical connection, portable meter with one or more conducting wires
Calculation machine disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable medium, which can be, any includes or storage program has
Shape medium, the program can be commanded execution system, device or device use or in connection.And in the application
In, computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, wherein
Carry computer-readable program code.The data-signal of this propagation can take various forms, including but not limited to electric
Magnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable Jie
Any computer-readable medium other than matter, the computer-readable medium can be sent, propagated or transmitted for being held by instruction
Row system, device or device use or program in connection.The program code for including on computer-readable medium
It can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. or above-mentioned any conjunction
Suitable combination.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as C language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include first acquisition unit, the first generation unit, second acquisition unit, the second generation unit, third generation unit and push unit.
Wherein, the title of these units does not constitute the restriction to the unit itself under certain conditions, for example, first acquisition unit is also
It can be described as " for obtaining the unit of the attribute information of target user ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment；It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: the attribute information of target user is obtained；First eigenvector is generated according to the attribute information of target user；Obtain target pair
The recommendation information of elephant；Second feature vector is generated according to recommendation information；Based on first eigenvector, second feature vector and pre-
First trained prediction model generates target user to the response intention of recommendation information；The response meaning generated in response to prediction model
To instruction target users did respond recommendation information, recommendation information is pushed to the terminal of target user.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for pushed information, comprising:
Obtain the attribute information of target user；
First eigenvector is generated according to the attribute information of the target user；
Obtain the recommendation information of target object；
Second feature vector is generated according to the recommendation information；
Based on the first eigenvector, the second feature vector and prediction model trained in advance, the target is generated
Response intention of the user to the recommendation information；
Recommendation information described in the target users did respond, Xiang Suoshu mesh are indicated in response to the response intention that the prediction model generates
The terminal for marking user pushes the recommendation information.
2. according to the method described in claim 1, wherein, the method also includes:
Obtain the attribute information of the target object；
Third feature vector is generated according to the attribute information of the target object；And
It is described based on the first eigenvector, the second feature vector and prediction model trained in advance, described in generation
Response intention of the target user to the recommendation information, comprising:
Third feature vector described in the first eigenvector, the second feature vector sum is input to prediction trained in advance
Model generates the target user to the response intention of the recommendation information.
3. according to the method described in claim 1, wherein, the recommendation information is generated via following steps:
Selection is combined for the recommendation information segment in the pre-set recommendation information set of segments of the target object, is obtained
To the set of recommendation information fragment combination；
For the recommendation information fragment combination in the set: generating the feature vector of the recommendation information fragment combination；This is pushed away
Feature vector, the first eigenvector and the second feature vector for recommending information segment combination are input to training in advance
Rating Model generates the score of the recommendation information fragment combination；
The recommendation information is generated according to the recommendation information fragment combination that the set mid-score meets preset condition.
4. according to the method described in claim 3, wherein, the recommendation that preset condition is met according to the set mid-score
It ceases fragment combination and generates the recommendation information, comprising:
Obtain the acquisition modes information of the pre-set target object；
Merge recommendation information fragment combination and the acquisition modes information that the set mid-score meets preset condition, obtains institute
State recommendation information.
5. method according to any of claims 1-4, wherein described to generate second feature according to the recommendation information
Vector, comprising:
Obtain at least one in the following item of information that the recommendation information includes: keyword, scene information and functional information；
According to second feature vector described in acquired item of information.
6. a kind of device for pushed information, comprising:
First acquisition unit is configured to obtain the attribute information of target user；
First generation unit is configured to generate first eigenvector according to the attribute information of the target user；
Second acquisition unit is configured to obtain the recommendation information of target object；
Second generation unit is configured to generate second feature vector according to the recommendation information；
Third generation unit is configured to based on the first eigenvector, the second feature vector and training in advance
Prediction model generates the target user to the response intention of the recommendation information；
Push unit is configured in response to the response intention that the prediction model generates and indicates described in the target users did respond
The terminal of recommendation information, Xiang Suoshu target user pushes the recommendation information.
7. device according to claim 6, wherein described device further include:
Third acquiring unit is configured to obtain the attribute information of the target object；
4th generation unit is configured to generate third feature vector according to the attribute information of the target object；And
The third generation unit, is further configured to:
Third feature vector described in the first eigenvector, the second feature vector sum is input to prediction trained in advance
Model generates the target user to the response intention of the recommendation information.
8. device according to claim 6, wherein described device further includes recommendation information generation unit, the recommendation
Ceasing generation unit includes:
Subelement is combined, is configured to select the recommendation in the pre-set recommendation information set of segments of the target object
Information segment is combined, and obtains the set of recommendation information fragment combination；
First generates subelement, is configured to for the recommendation information fragment combination in the set: generating the recommendation information piece
The feature vector of Duan Zuhe；By the feature vector of the recommendation information fragment combination, the first eigenvector and described second
Feature vector is input to Rating Model trained in advance, generates the score of the recommendation information fragment combination；
Second generates subelement, and the recommendation information fragment combination for being configured to meet preset condition according to the set mid-score is raw
At the recommendation information.
9. device according to claim 8, wherein the recommendation information generates subelement, is further configured to:
First obtains subelement, is configured to obtain the acquisition modes information of the pre-set target object；
Merge subelement, is configured to merge the set mid-score and meets the recommendation information fragment combination of preset condition and described
Acquisition modes information obtains the recommendation information.
10. the device according to any one of claim 6-9, wherein second generation unit, comprising:
Second obtains subelement, is configured to obtain at least one in the following item of information that the recommendation information includes: crucial
Word, scene information and functional information；
Third generates subelement, generates the second feature vector according to acquired item of information.
11. a kind of electronic equipment, comprising:
One or more processors；
Storage device is stored thereon with one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, such as right is realized when which is executed by processor
It is required that any method in 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811352882.2A CN109522483B (en) | 2018-11-14 | 2018-11-14 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811352882.2A CN109522483B (en) | 2018-11-14 | 2018-11-14 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109522483A true CN109522483A (en) | 2019-03-26 |
| CN109522483B CN109522483B (en) | 2022-04-12 |
Family
ID=65777763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811352882.2A Active CN109522483B (en) | 2018-11-14 | 2018-11-14 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522483B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109902446A (en) * | 2019-04-09 | 2019-06-18 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information prediction model |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110363574A (en) * | 2019-06-26 | 2019-10-22 | 腾讯科技（深圳）有限公司 | Products Show method, apparatus, electronic equipment and readable medium |
| CN110400166A (en) * | 2019-06-24 | 2019-11-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for selecting the official documents and correspondence pushed to target user |
| CN110750658A (en) * | 2019-09-18 | 2020-02-04 | 平安科技（深圳）有限公司 | Recommendation method of media resource, server and computer readable storage medium |
| CN110910180A (en) * | 2019-12-02 | 2020-03-24 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN110929209A (en) * | 2019-12-06 | 2020-03-27 | 北京百度网讯科技有限公司 | Method and device for sending information |
| CN111061956A (en) * | 2019-12-24 | 2020-04-24 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN111143543A (en) * | 2019-12-04 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Object recommendation method, device, equipment and medium |
| CN111857331A (en) * | 2020-06-16 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method, system, device and storage medium for determining user scene |
| CN111859220A (en) * | 2020-07-24 | 2020-10-30 | 北京字节跳动网络技术有限公司 | Method and device for displaying information |
| CN111914077A (en) * | 2020-08-06 | 2020-11-10 | 平安科技（深圳）有限公司 | Customized speech recommendation method, device, computer equipment and storage medium |
| CN111914820A (en) * | 2019-05-09 | 2020-11-10 | 百度在线网络技术（北京）有限公司 | Qualification auditing method and device |
| CN112035736A (en) * | 2020-07-31 | 2020-12-04 | 北京达佳互联信息技术有限公司 | Information pushing method and device and server |
| CN112148994A (en) * | 2020-10-23 | 2020-12-29 | 腾讯科技（深圳）有限公司 | Information push effect evaluation method and device, electronic equipment and storage medium |
| CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| WO2021203913A1 (en) * | 2020-04-08 | 2021-10-14 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating prediction information, electronic device, and computer-readable medium |
| CN113609397A (en) * | 2021-08-16 | 2021-11-05 | 北京沃东天骏信息技术有限公司 | Method and device for pushing information |
| US20230088171A1 (en) * | 2020-05-19 | 2023-03-23 | Huawei Technologies Co., Ltd. | Method and apparatus for training search recommendation model, and method and apparatus for sorting search results |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004043069A1 (en) * | 2002-11-08 | 2004-05-21 | Koninklijke Philips Electronics N.V. | Apparatus and method to provide a recommendation of content |
| US20110238730A1 (en) * | 2008-07-24 | 2011-09-29 | Alibaba Group Holding Limited | Correlated Information Recommendation |
| CN103971265A (en) * | 2013-01-31 | 2014-08-06 | 三星电子株式会社 | User Terminal And Method And System For Providing Advertisement |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106295832A (en) * | 2015-05-12 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Product information method for pushing and device |
| CN106528745A (en) * | 2016-10-27 | 2017-03-22 | 北京奇虎科技有限公司 | Method and device for recommending resources on mobile terminal, and mobile terminal |
| CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
| US20180020250A1 (en) * | 2015-09-08 | 2018-01-18 | Tencent Technology (Shenzhen) Company Limited | Recommendation information pushing method, server, and storage medium |
-
2018
- 2018-11-14 CN CN201811352882.2A patent/CN109522483B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004043069A1 (en) * | 2002-11-08 | 2004-05-21 | Koninklijke Philips Electronics N.V. | Apparatus and method to provide a recommendation of content |
| US20110238730A1 (en) * | 2008-07-24 | 2011-09-29 | Alibaba Group Holding Limited | Correlated Information Recommendation |
| CN103971265A (en) * | 2013-01-31 | 2014-08-06 | 三星电子株式会社 | User Terminal And Method And System For Providing Advertisement |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106295832A (en) * | 2015-05-12 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Product information method for pushing and device |
| US20180020250A1 (en) * | 2015-09-08 | 2018-01-18 | Tencent Technology (Shenzhen) Company Limited | Recommendation information pushing method, server, and storage medium |
| CN106528745A (en) * | 2016-10-27 | 2017-03-22 | 北京奇虎科技有限公司 | Method and device for recommending resources on mobile terminal, and mobile terminal |
| CN106649774A (en) * | 2016-12-27 | 2017-05-10 | 北京百度网讯科技有限公司 | Artificial intelligence-based object pushing method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| OLIVER DENNINGER: "Recommending relevant code artifacts for change requests using multiple predictors", 《RECOMMENDATION SYSTEMS FOR SOFTWARE ENGINEERING》 * |
| 赵相忠 等: "网络推荐信息对女性消费者购买意愿影响研究", 《商业研究》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109902446A (en) * | 2019-04-09 | 2019-06-18 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information prediction model |
| CN111914820A (en) * | 2019-05-09 | 2020-11-10 | 百度在线网络技术（北京）有限公司 | Qualification auditing method and device |
| CN110119477A (en) * | 2019-05-14 | 2019-08-13 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method, device and storage medium |
| CN110119477B (en) * | 2019-05-14 | 2024-02-27 | 腾讯科技（深圳）有限公司 | Information pushing method, device and storage medium |
| CN110400166A (en) * | 2019-06-24 | 2019-11-01 | 阿里巴巴集团控股有限公司 | The method and apparatus for selecting the official documents and correspondence pushed to target user |
| CN110363574A (en) * | 2019-06-26 | 2019-10-22 | 腾讯科技（深圳）有限公司 | Products Show method, apparatus, electronic equipment and readable medium |
| CN110750658A (en) * | 2019-09-18 | 2020-02-04 | 平安科技（深圳）有限公司 | Recommendation method of media resource, server and computer readable storage medium |
| CN112749296B (en) * | 2019-10-31 | 2024-01-26 | 北京达佳互联信息技术有限公司 | Video recommendation method, device, server and storage medium |
| CN112749296A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Video recommendation method and device, server and storage medium |
| CN110910180A (en) * | 2019-12-02 | 2020-03-24 | 北京嘀嘀无限科技发展有限公司 | Information pushing method and device, electronic equipment and storage medium |
| CN111143543A (en) * | 2019-12-04 | 2020-05-12 | 北京达佳互联信息技术有限公司 | Object recommendation method, device, equipment and medium |
| CN110929209A (en) * | 2019-12-06 | 2020-03-27 | 北京百度网讯科技有限公司 | Method and device for sending information |
| CN110929209B (en) * | 2019-12-06 | 2023-06-20 | 北京百度网讯科技有限公司 | Method and device for transmitting information |
| US11412070B2 (en) | 2019-12-24 | 2022-08-09 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for generating information |
| CN111061956A (en) * | 2019-12-24 | 2020-04-24 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| WO2021203913A1 (en) * | 2020-04-08 | 2021-10-14 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating prediction information, electronic device, and computer-readable medium |
| US20230088171A1 (en) * | 2020-05-19 | 2023-03-23 | Huawei Technologies Co., Ltd. | Method and apparatus for training search recommendation model, and method and apparatus for sorting search results |
| CN111857331A (en) * | 2020-06-16 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Method, system, device and storage medium for determining user scene |
| CN111859220A (en) * | 2020-07-24 | 2020-10-30 | 北京字节跳动网络技术有限公司 | Method and device for displaying information |
| CN112035736B (en) * | 2020-07-31 | 2023-12-26 | 北京达佳互联信息技术有限公司 | Information pushing method, device and server |
| CN112035736A (en) * | 2020-07-31 | 2020-12-04 | 北京达佳互联信息技术有限公司 | Information pushing method and device and server |
| CN111914077A (en) * | 2020-08-06 | 2020-11-10 | 平安科技（深圳）有限公司 | Customized speech recommendation method, device, computer equipment and storage medium |
| CN112148994A (en) * | 2020-10-23 | 2020-12-29 | 腾讯科技（深圳）有限公司 | Information push effect evaluation method and device, electronic equipment and storage medium |
| CN112148994B (en) * | 2020-10-23 | 2024-04-19 | 腾讯科技（深圳）有限公司 | Information push effect evaluation method and device, electronic equipment and storage medium |
| CN113609397A (en) * | 2021-08-16 | 2021-11-05 | 北京沃东天骏信息技术有限公司 | Method and device for pushing information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109522483B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522483A (en) | Method and apparatus for pushed information | |
| CN107908789A (en) | Method and apparatus for generating information | |
| CN109460513A (en) | Method and apparatus for generating clicking rate prediction model | |
| CN107491534A (en) | Information processing method and device | |
| CN108153901A (en) | The information-pushing method and device of knowledge based collection of illustrative plates | |
| US20200045122A1 (en) | Method and apparatus for pushing information | |
| CN109983455A (en) | The diversified media research result on online social networks | |
| CN107908740A (en) | Information output method and device | |
| CN109543058A (en) | For the method for detection image, electronic equipment and computer-readable medium | |
| CN109325213A (en) | Method and apparatus for labeled data | |
| CN108989882A (en) | Method and apparatus for exporting the snatch of music in video | |
| CN109697239A (en) | Method for generating the method for graph text information and for generating image data base | |
| US11200591B2 (en) | Electronic content based on neural networks | |
| CN109522486A (en) | Method and apparatus for match information | |
| CN107590246A (en) | Method and apparatus for pushed information | |
| CN109299477A (en) | Method and apparatus for generating text header | |
| CN109635094A (en) | Method and apparatus for generating answer | |
| CN108429816A (en) | Method and apparatus for generating information | |
| CN110413872A (en) | Method and apparatus for showing information | |
| CN107451785A (en) | Method and apparatus for output information | |
| CN109389660A (en) | Image generating method and device | |
| CN109325178A (en) | Method and apparatus for handling information | |
| CN110232920A (en) | Method of speech processing and device | |
| CN109873756A (en) | Method and apparatus for sending information | |
| CN109284342A (en) | Method and apparatus for output information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |